CtrlAltDebrief

Gemma 4 31B

GoogleReleased Apr 2, 2026
VisionTool useReasoningStructured output
Compare Gemma 4 31BCount tokens for Gemma 4 31B
Context
256K
Max output
256K
Serving providers
2
Cheapest input
$0.14 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
35 t/s
tokens / second
Time to first token
1.11s
latency
Headline indices
Intelligence Index
14.7
of 100
Coding Index
43.4
of 100
Frozen Sep 9, 2026
Agentic Index
11.1
of 100
Frozen Sep 9, 2026
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
AA-BriefcaseUndated0%default—
Automation Bench0.0default—
CritPt1%default—
EvalComputeProxyFrozen Aug 18, 2026498.3default—
GDPval v2Frozen Aug 18, 2026810.6default—
GPQA Diamond86%default—
Harvey Lab0.5default—
Humanity's Last Exam24%default—
IFBench76%default—
IT-Bench SRE37%default—
Long-Context Reasoning70%default—
MMMU-Pro73%default—
Omniscience-47.9default—
Omniscience Accuracy0.2default—
Omniscience Non Hallucination0.2reasoning: false—
SciCode45%default—
Terminal Bench400default—
TerminalBench Hard36%default—
TerminalBench v2.143%default—
τ-bench Banking15%default—
τ²-bench65%reasoning: false—
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
We cannot tell whether this benchmark is still being published. Treat these scores as undated.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.14 to $0.99 per 1M tokens across 2 providers, so the dearest route costs 607% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
Amazon BedrockCheapest$0.14$0.401
Standardbedrock_mantle/google.gemma-4-31b
ComponentUnitStandard
Text input/1M tok$0.14
Text output/1M tok$0.40
Cerebras$0.99$1.491

Price history

listed seller prices, input and output per 1M tokens
Input Output
$0.00$0.10$0.20$0.30$0.40Jun 12Jun 22Sep 2$0.40$0.14

Cost calculator

estimate your monthly spend on this model
$60
estimated / month

Model IDs

copy the exact identifier for your platform
bedrock_mantle/google.gemma-4-31bcerebras/gemma-4-31b

Frequently asked questions

Gemma 4 31B pricing, context and availability

How much does Gemma 4 31B cost?

Gemma 4 31B costs $0.14 per 1M input tokens from Amazon Bedrock, and $0.40 per 1M output tokens from Amazon Bedrock. Across 2 serving providers, input prices range from $0.14 to $0.99 per 1M tokens.

What is the context window of Gemma 4 31B?

Gemma 4 31B accepts up to 256K tokens of context and can return up to 256K output tokens.

Which providers serve Gemma 4 31B?

Gemma 4 31B is available from 2 serving providers, each with its own pricing and model ID. Amazon Bedrock is currently the cheapest.

What can Gemma 4 31B do?

Gemma 4 31B supports image input (vision), tool use, reasoning and structured output.

Other Google models

compare pricing across the Google lineup
Gemma 4 31B$0.09/1M · 13 providersGemma 4 26B A4B $0.07/1M · 10 providersGemma 3 27B$0.08/1M · 8 providersGemini 2.5 Flash$0.15/1M · 8 providersGemini 3.7 Flash$0.75/1M · 7 providersGemini 2.5 Pro$1.25/1M · 7 providersGemini 3.5 Flash$1.50/1M · 7 providersGemini 3.1 Flash Lite$0.25/1M · 6 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI